Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Support requests

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    dar
    -0.07
    另外
    -0.07
    ih
    -0.06
     Forces
    -0.06
    _CLIENT
    -0.06
    $config
    -0.06
    ději
    -0.06
    overrides
    -0.06
    전히
    -0.06
    мотреть
    -0.06
    POSITIVE LOGITS
    ],$
    0.07
    .training
    0.07
    .Screen
    0.07
     cane
    0.06
    valuation
    0.06
     faiz
    0.06
    买
    0.06
    暂
    0.06
     Fiesta
    0.06
     disagreement
    0.06
    Act Density 0.019%

    No Known Activations